Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of animals, with a particular focus on tigers

    oai_token-act-pair · gpt-3.5-turbo

    signals indicating the presence of tigers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cknow
    -0.75
    ASED
    -0.74
     Statements
    -0.73
    ALLY
    -0.72
     Statement
    -0.71
    nce
    -0.69
    ABLE
    -0.69
    Commission
    -0.67
    States
    -0.67
    Transaction
    -0.66
    POSITIVE LOGITS
    aurus
    1.16
    '
    1.05
    hip
    1.03
    ongs
    1.03
    mith
    1.02
    hips
    1.02
    uits
    1.01
    paces
    0.99
    ervatives
    0.94
    folk
    0.94
    Act Density 0.125%

    No Known Activations